HM_ADET: a hybrid model for automatic detection of eyelid tumors based on photographic images.

"availability of data and materials the source code and example data used in this study can be accessed at github ( https://github com/jiangjiewei/eyelid-tumors-hm_adet )."

"availability of data and materials the source code and example data used in this study can be accessed at github ( https://github com/jiangjiewei/eyelid-tumors-hm_adet )."

"Declarations Ethics approval and consent to participateApproval from the institutional review board of Ningbo Eye Hospital (NEH) was obtained (identifier, 2021-qtky-44), and the study protocol was performed following the Declaration of Helsinki principles. Consent for publicationAll anonymous fundus images were transferred to research investigators for inclusion. Informed consent was exempted, due to the retrospective nature of the data acquisition and the use of deidentified images. Competing interestsThe authors have no potential competing interests to disclose. Competing interests The authors have no potential competing interests to disclose."

"Funding This study was funded by the National Natural Science Foundation of China (grant no. 62276210, 82201148, 61775180, 62376215, 62301428), the Natural Science Basic Research Program of Shaanxi Province (grant no. 2022JM-380), the Natural Science Foundation of Zhejiang Province (grant no. LQ22H120002), the Medical Health Science and Technology Project of Zhejiang Province (grant no. 2022RC069, 2023KY1140), the Natural Science Foundation of Ningbo (grant no. 2023J390), the Ningbo Top Medical and Health Research Program (grant no. 2023030716), and the Postgraduate Innovation Fund of Xi'an University of Posts and Telecommunications (grant no. CXJJZL2022008)."